Table 4 Top biological process and molecular function classes predicted by each type of feature
From: Evaluating a variety of text-mined features for automatic protein function prediction with GOstruct
Original co-mentions | |||||||
|---|---|---|---|---|---|---|---|
GO ID | Name | # Predictions | Precision | Recall | F-measure | Depth | IC |
GO:0009987 | cellular process | 6,164 | 0.812 | 0.875 | 0.842 | 1 | 0.66 |
GO:0044699 | single-organism process | 4,849 | 0.743 | 0.765 | 0.754 | 1 | 0.96 |
GO:0044763 | single-organism cellular process | 4,295 | 0.681 | 0.714 | 0.697 | 2 | 1.20 |
GO:0008152 | metabolic process | 3,893 | 0.644 | 0.726 | 0.682 | 1 | 1.22 |
GO:0065007 | biological regulation | 3,615 | 0.691 | 0.629 | 0.658 | 1 | 0.90 |
GO:0071704 | organic substance metabolic process | 3,489 | 0.611 | 0.677 | 0.643 | 2 | 1.42 |
GO:0050789 | regulation of biological process | 3,350 | 0.668 | 0.601 | 0.633 | 2 | 0.97 |
GO:0044238 | primary metabolic process | 3,337 | 0.593 | 0.655 | 0.623 | 2 | 1.56 |
GO:0044237 | cellular metabolic process | 3,268 | 0.590 | 0.644 | 0.616 | 2 | 1.49 |
GO:0050794 | regulation of cellular process | 3,156 | 0.648 | 0.583 | 0.614 | 3 | 1.11 |
GO:0050896 | response to stimulus | 2,968 | 0.606 | 0.590 | 0.597 | 1 | 1.62 |
GO:0043170 | macromolecule metabolic process | 2,640 | 0.548 | 0.618 | 0.581 | 3 | 1.77 |
Enhanced co-mentions | |||||||
GO ID | Name | # Predictions | Precision | Recall | F-measure | Depth | IC |
GO:0009987 | cellular process | 6,223 | 0.816 | 0.887 | 0.850 | 1 | 0.66 |
GO:0007076 | mitotic chromosome condensation | 6 | 0.833 | 0.714 | 0.769 | 4 | 8.58 |
GO:0006323 | DNA packaging | 6 | 0.833 | 0.714 | 0.769 | 3 | 7.81 |
GO:0044699 | single-organism process | 4,957 | 0.744 | 0.783 | 0.763 | 1 | 0.96 |
GO:0044763 | single-organism cellular process | 4,423 | 0.682 | 0.736 | 0.708 | 2 | 1.20 |
GO:0008152 | metabolic process | 3,887 | 0.643 | 0.723 | 0.681 | 1 | 1.22 |
GO:0065007 | biological regulation | 3,701 | 0.683 | 0.636 | 0.659 | 1 | 0.90 |
GO:0050789 | regulation of biological process | 3,453 | 0.662 | 0.613 | 0.637 | 2 | 0.97 |
GO:0071704 | organic substance metabolic process | 3,491 | 0.605 | 0.670 | 0.636 | 2 | 1.42 |
GO:0043252 | sodium-independent organic anion transport | 11 | 0.636 | 0.583 | 0.608 | 7 | 8.50 |
GO:0000398 | mRNA splicing, via spliceosome | 140 | 0.492 | 0.697 | 0.577 | 10 | 5.88 |
GO:0006607 | NLS-bearing protein import into nucleus | 15 | 0.533 | 0.571 | 0.551 | 6 | 8.50 |
Bag-of-words | |||||||
GO ID | Name | # Predictions | Precision | Recall | F-measure | Depth | IC |
GO:0009987 | cellular process | 6,005 | 0.820 | 0.869 | 0.844 | 1 | 0.66 |
GO:0044699 | single-organism process | 4,940 | 0.754 | 0.799 | 0.776 | 1 | 0.96 |
GO:0044763 | single-organism cellular process | 4,449 | 0.696 | 0.764 | 0.728 | 2 | 1.20 |
GO:0043252 | sodium-independent organic anion transport | 8 | 0.875 | 0.583 | 0.700 | 7 | 8.50 |
GO:0065007 | biological regulation | 3,865 | 0.698 | 0.686 | 0.692 | 1 | 0.90 |
GO:0008152 | metabolic process | 3,870 | 0.647 | 0.733 | 0.688 | 1 | 1.22 |
GO:0050789 | regulation of biological process | 3,597 | 0.680 | 0.663 | 0.671 | 2 | 0.97 |
GO:0006479 | protein methylation | 13 | 0.615 | 0.727 | 0.666 | 8 | 6.52 |
GO:0051568 | histone H3-K4 methylation | 13 | 0.615 | 0.727 | 0.666 | 11 | 7.94 |
GO:0007076 | mitotic chromosome condensation | 5 | 0.800 | 0.571 | 0.666 | 4 | 8.58 |
GO:0050794 | regulation of cellular process | 3,440 | 0.657 | 0.651 | 0.654 | 3 | 1.11 |
GO:0006497 | protein lipidation | 9 | 0.889 | 0.500 | 0.640 | 7 | 6.79 |
Co-mentions + Bag-of-words | |||||||
GO ID | Name | # Predictions | Precision | Recall | F-measure | Depth | IC |
GO:0009987 | cellular process | 6,420 | 0.813 | 0.913 | 0.860 | 1 | 0.66 |
GO:0044699 | single-organism process | 5,338 | 0.736 | 0.834 | 0.782 | 1 | 0.96 |
GO:0044763 | single-organism cellular process | 4,862 | 0.674 | 0.800 | 0.731 | 2 | 1.20 |
GO:0065007 | biological regulation | 4,445 | 0.669 | 0.749 | 0.707 | 1 | 0.90 |
GO:0008152 | metabolic process | 4,252 | 0.638 | 0.785 | 0.704 | 1 | 1.22 |
GO:0050789 | regulation of biological process | 4,199 | 0.650 | 0.733 | 0.689 | 2 | 0.97 |
GO:0050794 | regulation of cellular process | 4,046 | 0.626 | 0.723 | 0.671 | 3 | 1.11 |
GO:0043252 | sodium-independent organic anion transport | 15 | 0.600 | 0.750 | 0.667 | 7 | 8.50 |
GO:0071704 | organic substance metabolic process | 3,883 | 0.602 | 0.743 | 0.665 | 2 | 1.42 |
GO:0043170 | macromolecule metabolic process | 3,007 | 0.540 | 0.694 | 0.607 | 3 | 1.77 |
GO:0051716 | cellular response to stimulus | 3,176 | 0.520 | 0.674 | 0.587 | 3 | 1.89 |
GO:0006386 | termination of RNA polymerase III transcription | 12 | 0.583 | 0.583 | 0.583 | 7 | 8.18 |